← Back to community benchmarks

Qwen3.5-35B-A3B

M1 Max (24c) · 32 GB · 4bit · 2026-03-10
Performance
4k
tokens
440.6
PP tok/s
54.4
TG tok/s
9296
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.2.6
macOS macOS 15.6.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 406.2 59.2 20.1 GB view
4k 440.6 54.4 20.2 GB current
Batching Results
Batch Size TG tok/s Speedup
59.2 1.00×
80.4 1.36×
96.6 1.63×